Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ It achieves the following results on the evaluation set:
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
| 23 |
-
Trained on single ID token 5K dataset filtered to
|
| 24 |
|
| 25 |
lora_alpha = 128
|
| 26 |
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
| 23 |
+
Trained on single ID token 5K dataset filtered to 10k sequences (20% for test data = 2000)
|
| 24 |
|
| 25 |
lora_alpha = 128
|
| 26 |
|